CN110598905A - Method for predicting thermal runaway of rail-to-rail cable through multipoint data acquisition - Google Patents
Method for predicting thermal runaway of rail-to-rail cable through multipoint data acquisition Download PDFInfo
- Publication number
- CN110598905A CN110598905A CN201910730552.0A CN201910730552A CN110598905A CN 110598905 A CN110598905 A CN 110598905A CN 201910730552 A CN201910730552 A CN 201910730552A CN 110598905 A CN110598905 A CN 110598905A
- Authority
- CN
- China
- Prior art keywords
- data
- cable
- electric energy
- thermal runaway
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000004140 cleaning Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 6
- 238000002360 preparation method Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 15
- 230000009467 reduction Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000008094 contradictory effect Effects 0.000 claims description 3
- 210000002364 input neuron Anatomy 0.000 claims description 3
- 210000004205 output neuron Anatomy 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 4
- 238000001514 detection method Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 10
- 230000003287 optical effect Effects 0.000 description 9
- 239000013307 optical fiber Substances 0.000 description 8
- 230000008859 change Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G06Q50/40—
Abstract
The invention relates to the technical field of rail transit monitoring, in particular to a method for predicting thermal runaway of a rail transit cable through multipoint data acquisition; s1, acquiring and arranging data related to cable thermal runaway prediction; s101, a data preparation step, namely acquiring data related to the use of the rail transit cable; s102, a data arrangement step, namely cleaning the data related to the cable use and constructing the data related to the cleaned cable use based on a time unit; s2, normalizing data; s3 machine learning; compared with the prior art, multipoint data acquisition is adopted, so that mutual influence among acquisition points is avoided; and (3) rapidly constructing a prediction model between the cable data and the predicted electric energy data by adopting a neural network algorithm according to the collected and cleaned data, predicting the electric energy data in a certain time in the future according to the existing cable data according to the model, and judging whether thermal runaway can occur or not.
Description
Technical Field
The invention relates to the technical field of rail transit monitoring, in particular to a method for predicting thermal runaway of a rail transit cable through multipoint data acquisition.
Background
In rail transit, the cable as a power supply source is very important, so that the in-and-out of parameters such as temperature and the like need to be monitored in real time. For example, chinese patent discloses a method and a system for monitoring abnormal temperature rise of a power supply traction cable based on distributed optical fiber temperature measurement, patent No. 201610958261.3. Wherein the description is as follows: the distributed optical fiber detection locator comprises a Rayleigh or Brillouin scattering distributed optical fiber vibration and strain sensor, a detection instrument and a mode identification unit, wherein a temperature detection optical cable is fixed on a power supply traction cable in parallel in a physical contact mode such as an anchor ear or a clamp, if the power supply traction cable is abnormally heated, the temperature of the temperature detection optical cable is increased along with the temperature detection optical cable, an optical signal in the temperature detection optical fiber is modulated, and the signal is captured by the distributed optical fiber detection locator to form early warning information; the temperatures of different positions of the temperature detection optical cable are given by the Brillouin scattering signal, and the information such as the real-time temperature, temperature change or distribution position and the like of the temperature detection optical cable is obtained through signal processing of the mode identification unit, so that the information such as the temperature, temperature change and temperature change position and the like of the temperature detection optical cable on the power supply traction cable in a certain space or time interval are obtained; after the distributed optical fiber detection positioning instrument performs comprehensive analysis and processing on the temperature information of the temperature detection optical cable, the judgment on the safety state of the power supply traction cable is formed, early warning information is formed, the early warning information is transmitted to the monitoring platform data center through a communication link, and the data center transmits the monitoring information to the user terminals with different authorities.
The technical scheme has the following defects that: the function of prejudging that the cable is possibly abnormal is lacked.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for predicting the thermal runaway of a rail transit cable through multipoint data acquisition.
The technical scheme of the invention is as follows:
a method for predicting thermal runaway of a rail-to-rail cable through multipoint data acquisition is characterized by comprising the following steps: it comprises the following steps:
s1, acquiring and arranging data related to cable thermal runaway prediction;
in the data arrangement step, data related to cable thermal runaway prediction are collected and arranged, so that the corresponding cable thermal runaway condition can be predicted through an algorithm.
Specifically, the data acquiring and sorting step includes the following steps:
s101, a data preparation step, namely acquiring data related to the use of the rail transit cable;
in this step, the data of the cable includes monitoring data of the cable, and the monitoring data is collected once per second; the monitoring data are cable temperature and electric energy data.
S102, data arrangement, namely cleaning the data related to the cable use and constructing the data related to the cleaned cable use based on a time unit. The data processing is mainly based on the realization of data processing, so that the high-quality data is ensured, and the accuracy of the result is improved, and therefore, the data processing needs to be carried out on the acquired data. The data sorting firstly needs to clean the data, and the invention establishes a corresponding cleaning rule to convert the data with low quality into the data meeting the data quality requirement. The cleaning rules include: and (4) vacant assignment: in the invention, the average value or the intermediate value of the variable or adjacent interpolation value of a section of travel is mainly adopted to assign the vacant variable. Error value removal: whether the data are qualified or not is checked by setting a reasonable value range, namely a threshold value, of each variable of the cable use related data, and the data beyond a normal range are deleted or corrected. And (3) cross checking: logically unreasonable or contradictory data is deleted or corrected by setting mutual constraints and dependencies of cable usage related data. After the data is cleaned, data construction is carried out on the basis of time units, namely, collected data are integrated according to the time sequence. Time units may be based on milliseconds, seconds, minutes, and the like.
S2, normalizing data;
normalizing the cleaned data of S1:
T*＝T-Tmin/Tmax-Tmin
wherein T is the cable temperature; tmin is the minimum value of the cable temperature; tmax is the maximum value of the cable temperature.
Normalization of measured power data:
P*＝P/Pmax
wherein, P is electric energy data; pmax is the maximum value of the electric energy.
S3 machine learning;
after data normalization processing, part of multipoint cable temperature data and electric energy data which can be used for machine learning are obtained through screening and correction, and then the data are used for training.
Building a 3-layer neural network of 28n input neurons and 8n output neurons, wherein a sigmoid function is selected as an activation function of the network; a layer-by-layer training process: inputting 28 groups of cable temperature data T used in training into a noise reduction automatic coding machine model, training to obtain a mapping function f theta between a hidden layer and an input layer and a network parameter theta of the mapping function which is { W, b }, abandoning a mapping function g theta 'and a network parameter theta' thereof, obtaining hidden layer output y, and regarding reconstructed data y as an equivalent expression form of the cable temperature T after nonlinear conversion. Thereby completing the training of the first layer deep neural network.
And then inputting y into a next noise reduction automatic coding machine model, training to obtain a mapping function f theta (2) and a parameter theta (2) { W, b }, abandoning the mapping function g theta '(2) and a network parameter theta' (2) thereof in the second noise reduction automatic coding machine model, obtaining y (1) subjected to nonlinear conversion of f theta (2), and regarding the y as another equivalent expression form of the cable temperature T. This completes the training of the second layer deep neural network. The layer-by-layer training process of the multiple layers is completed according to the above mode.
And (3) fine adjustment process: the network parameters obtained by the noise reduction automatic coding machine layers are used for initializing a deep network, then the preprocessed cable temperature T data is used as input, the preprocessed 8 groups of electric energy data are used as output, the BP algorithm is used for iterating the network parameters of the neural network, and finally the electric energy prediction model of the multipoint collected data is obtained.
And defining a normal electric energy interval, importing the cable data obtained in real time into an electric energy prediction model, and when the predicted electric energy obtained after a plurality of time nodes is in the normal electric energy interval, the cable has no thermal runaway danger, otherwise, early warning is carried out, and countdown is carried out on the danger to be generated.
The invention has the beneficial effects that: compared with the prior art, multipoint data acquisition is adopted, so that mutual influence among acquisition points is avoided; and (3) rapidly constructing a prediction model between the cable data and the predicted electric energy data by adopting a neural network algorithm according to the collected and cleaned data, predicting the electric energy data in a certain time in the future according to the existing cable data according to the model, and judging whether thermal runaway can occur or not.
Drawings
FIG. 1 is a diagram of the hardware configuration of the present invention;
FIG. 2 is a flow chart of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings:
as shown in fig. 1, a hardware system is constructed. The monitoring system comprises a cable to be monitored, temperature measuring optical cables (optical fibers) connected to a plurality of sites, a first engineering machine connected with the optical fibers, an electric quantity acquisition unit, a monitoring screen, the Internet and other modes, wherein the first engineering machine uploads temperature data to an upper machine in a wired or wireless mode, meanwhile, the electric quantity acquisition unit is arranged on the temperature measuring sites of the cable to be monitored through a plurality of electric quantity acquisition sensors and uploads the acquired electric quantity data to the upper machine, and the upper machine is interacted with managers through the monitoring screen, the Internet and other modes.
As shown in fig. 2, the present embodiment includes the following steps:
s1, acquiring and arranging data related to cable thermal runaway prediction;
in the data arrangement step, data related to cable thermal runaway prediction are collected and arranged, so that the corresponding cable thermal runaway condition can be predicted through an algorithm.
Specifically, the data acquiring and sorting step includes the following steps:
s101, a data preparation step, namely acquiring data related to the use of the rail transit cable;
in this step, the data of the cable includes monitoring data of the cable, and the monitoring data is collected once per second; the monitoring data are cable temperature and electric energy data. Specifically, the power data is a voltage.
S102, data arrangement, namely cleaning the data related to the cable use and constructing the data related to the cleaned cable use based on a time unit. The data processing is mainly based on the realization of data processing, so that the high-quality data is ensured, and the accuracy of the result is improved, and therefore, the data processing needs to be carried out on the acquired data. The data sorting firstly needs to clean the data, and the invention establishes a corresponding cleaning rule to convert the data with low quality into the data meeting the data quality requirement. The cleaning rules include: and (4) vacant assignment: in the invention, the average value or the intermediate value of the variable or adjacent interpolation value of a section of travel is mainly adopted to assign the vacant variable. Error value removal: whether the data are qualified or not is checked by setting a reasonable value range, namely a threshold value, of each variable of the cable use related data, and the data beyond a normal range are deleted or corrected. And (3) cross checking: logically unreasonable or contradictory data is deleted or corrected by setting mutual constraints and dependencies of cable usage related data. After the data is cleaned, data construction is carried out on the basis of time units, namely, collected data are integrated according to the time sequence. Time units may be based on milliseconds, seconds, minutes, and the like. The unit of time in this embodiment is seconds.
S2, normalizing data;
normalizing the cleaned data of S1:
T*＝T-Tmin/Tmax-Tmin
wherein T is the cable temperature; tmin is the minimum value of the cable temperature; tmax is the maximum value of the cable temperature.
Normalization of measured power data:
P*＝P/Pmax
wherein, P is electric energy data; pmax is the maximum value of the electric energy.
S3 machine learning;
after data normalization processing, part of multipoint cable temperature data and electric energy data which can be used for machine learning are obtained through screening and correction, and then the data are used for training.
Building a 3-layer neural network of 28n input neurons and 8n output neurons, wherein a sigmoid function is selected as an activation function of the network; a layer-by-layer training process: inputting 28 groups of cable temperature data T used in training into a noise reduction automatic coding machine model, training to obtain a mapping function f theta between a hidden layer and an input layer and a network parameter theta of the mapping function which is { W, b }, abandoning a mapping function g theta 'and a network parameter theta' thereof, obtaining hidden layer output y, and regarding reconstructed data y as an equivalent expression form of the cable temperature T after nonlinear conversion. Thereby completing the training of the first layer deep neural network.
And then inputting y into a next noise reduction automatic coding machine model, training to obtain a mapping function f theta (2) and a parameter theta (2) { W, b }, abandoning the mapping function g theta '(2) and a network parameter theta' (2) thereof in the second noise reduction automatic coding machine model, obtaining y (1) subjected to nonlinear conversion of f theta (2), and regarding the y as another equivalent expression form of the cable temperature T. This completes the training of the second layer deep neural network. The layer-by-layer training process of the multiple layers is completed according to the above mode.
And (3) fine adjustment process: the network parameters obtained by the noise reduction automatic coding machine layers are used for initializing a deep network, then the preprocessed cable temperature T data is used as input, the preprocessed 8 groups of electric energy data are used as output, the BP algorithm is used for iterating the network parameters of the neural network, and finally the electric energy prediction model of the multipoint collected data is obtained.
And defining a normal electric energy interval, importing the cable data obtained in real time into an electric energy prediction model, and when the predicted electric energy obtained after a plurality of time nodes is in the normal electric energy interval, the cable has no thermal runaway danger, otherwise, early warning is carried out, and countdown is carried out on the danger to be generated.
The foregoing embodiments and description have been presented only to illustrate the principles and preferred embodiments of the invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention as hereinafter claimed.
Claims (5)
1. A method for predicting thermal runaway of a rail-to-rail cable through multipoint data acquisition is characterized by comprising the following steps: it comprises the following steps:
s1, acquiring and arranging data related to cable thermal runaway prediction;
s2, normalizing data;
normalizing the cleaned data of S1:
T*＝T-Tmin/Tmax-Tmin
wherein T is the cable temperature; tmin is the minimum value of the cable temperature; tmax is the maximum value of the cable temperature.
Normalization of measured power data:
P*＝P/Pmax
wherein, P is electric energy data; pmax is the maximum value of the electric energy.
S3 machine learning;
building a 3-layer neural network of 28n input neurons and 8n output neurons, wherein a sigmoid function is selected as an activation function of the network; a layer-by-layer training process: inputting 28 groups of cable temperature data T used in training into a noise reduction automatic coding machine model, training to obtain a mapping function f theta between a hidden layer and an input layer and a network parameter theta of the mapping function which is { W, b }, abandoning a mapping function g theta 'and a network parameter theta' thereof, obtaining hidden layer output y, and regarding reconstructed data y as an equivalent expression form of the cable temperature T after nonlinear conversion; thereby completing the training of the first layer deep neural network;
inputting y into a next noise reduction automatic coding machine model, training to obtain a mapping function f theta (2) and a parameter theta (2) ═ W, b in the second noise reduction automatic coding machine model, discarding the mapping function g theta '(2) and a network parameter theta' (2), solving y (1) subjected to f theta (2) nonlinear conversion, and similarly regarding the y as another equivalent expression form of the cable temperature T; thus, the training of the second layer deep neural network is completed; the layer-by-layer training process of the multiple layers is completed according to the above mode.
2. The method for predicting rail transit cable thermal runaway through multipoint data collection according to claim 1, wherein: in the data collating step, data relating to the prediction of thermal runaway of the cable is collected and collated.
3. The method for predicting thermal runaway of rail transit cables through multipoint data collection as claimed in claim 2, wherein: the data acquisition and sorting step comprises the following processes:
s101, a data preparation step, namely acquiring data related to the use of the rail transit cable;
in this step, the data of the cable includes monitoring data of the cable, and the monitoring data is collected once per second; the monitoring data are cable temperature and electric energy data;
s102, a data arrangement step, namely cleaning the data related to the cable use and constructing the data related to the cleaned cable use based on a time unit; the data sorting firstly needs to clean the data, and the invention establishes a corresponding cleaning rule to convert the data with low quality into the data meeting the data quality requirement; the cleaning rules include: and (4) vacant assignment: in the invention, the average value or the intermediate value of the variable or adjacent interpolation value of a section of travel is mainly adopted to assign the vacant variable; error value removal: checking whether the data meets the requirements or not by setting a reasonable value range, namely a threshold value, of each variable of the cable use related data, and deleting or correcting the data beyond the normal range; and (3) cross checking: deleting or correcting logically unreasonable or contradictory data by setting mutual constraint and dependency relationship of related data used by the cable; after the data are cleaned, data construction is carried out based on time units, namely, the collected data are integrated according to the time sequence; time units may be based on milliseconds, seconds, minutes, and the like.
4. The method for predicting rail transit cable thermal runaway through multipoint data collection according to claim 3, wherein: the step S3 further includes a fine tuning process: the network parameters obtained by the noise reduction automatic coding machine layers are used for initializing a deep network, then the preprocessed cable temperature T data is used as input, the preprocessed 8 groups of electric energy data are used as output, the BP algorithm is used for iterating the network parameters of the neural network, and finally the electric energy prediction model of the multipoint collected data is obtained.
5. The method for predicting thermal runaway of rail transit cables through multipoint data collection according to claim 4, wherein the method comprises the following steps: the method further comprises the steps of defining a normal electric energy interval, importing the cable data obtained in real time into an electric energy prediction model, and when the predicted electric energy obtained after a plurality of time nodes is in the normal electric energy interval, enabling the cable not to have thermal runaway danger, otherwise, early warning and countdown on-coming danger.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730552.0A CN110598905A (en) | 2019-08-08 | 2019-08-08 | Method for predicting thermal runaway of rail-to-rail cable through multipoint data acquisition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730552.0A CN110598905A (en) | 2019-08-08 | 2019-08-08 | Method for predicting thermal runaway of rail-to-rail cable through multipoint data acquisition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110598905A true CN110598905A (en) | 2019-12-20 |
Family
ID=68853725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910730552.0A Pending CN110598905A (en) | 2019-08-08 | 2019-08-08 | Method for predicting thermal runaway of rail-to-rail cable through multipoint data acquisition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110598905A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809610A (en) * | 2023-02-08 | 2023-03-17 | 广东电网有限责任公司中山供电局 | Direct-buried three-core cable current-carrying capacity prediction method and system based on multi-step load |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104596656A (en) * | 2014-10-17 | 2015-05-06 | 芜湖扬宇机电技术开发有限公司 | Temperature early warning method of cable joint |
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN106650982A (en) * | 2016-08-30 | 2017-05-10 | 华北电力大学 | Depth learning power prediction method based on multi-point NWP |
| CN109978229A (en) * | 2019-02-12 | 2019-07-05 | 常伟 | The method that the full battery core multi-point temperature of a kind of pair of power battery pack and tie point temperature carry out thermal runaway prediction |
| CN110083908A (en) * | 2019-04-19 | 2019-08-02 | 陕西科技大学 | Cable conductor temperature predicting method based on finite element analysis |
-
2019
- 2019-08-08 CN CN201910730552.0A patent/CN110598905A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN104596656A (en) * | 2014-10-17 | 2015-05-06 | 芜湖扬宇机电技术开发有限公司 | Temperature early warning method of cable joint |
| CN106650982A (en) * | 2016-08-30 | 2017-05-10 | 华北电力大学 | Depth learning power prediction method based on multi-point NWP |
| CN109978229A (en) * | 2019-02-12 | 2019-07-05 | 常伟 | The method that the full battery core multi-point temperature of a kind of pair of power battery pack and tie point temperature carry out thermal runaway prediction |
| CN110083908A (en) * | 2019-04-19 | 2019-08-02 | 陕西科技大学 | Cable conductor temperature predicting method based on finite element analysis |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809610A (en) * | 2023-02-08 | 2023-03-17 | 广东电网有限责任公司中山供电局 | Direct-buried three-core cable current-carrying capacity prediction method and system based on multi-step load |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN109102189B (en) | Electrical equipment health management system and method | |
| KR102092185B1 (en) | Platform for analyzing electric motor health and analysis method using the same | |
| JP2020115311A (en) | Model integration device, model integration method, model integration program, inference system, inspection system and control system | |
| CN110361207B (en) | Intelligent train running gear online state prediction system and method thereof | |
| CN1862278A (en) | Method and system for predicting remaining life for motors featuring on-line insulation condition monitor | |
| CN112617862B (en) | Method for judging coupling strength between signals based on multichannel neural signal analysis | |
| US20220067584A1 (en) | Model generation apparatus, model generation method, computer-readable storage medium storing a model generation program, model generation system, inspection system, and monitoring system | |
| CN110598905A (en) | Method for predicting thermal runaway of rail-to-rail cable through multipoint data acquisition | |
| CN116046050B (en) | Environment monitoring method | |
| US9375183B2 (en) | Method for monitoring sensor degradation, patient monitor, patient monitor system, physiological sensor, and computer program product for a patient monitor | |
| CN112039073B (en) | Collaborative optimization method and system suitable for fault judgment of power distribution room equipment | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN108848571A (en) | A kind of rail traffic safety monitoring system and monitoring method based on MEMS sensor | |
| CN115238915A (en) | Industrial equipment fault prediction and health monitoring system | |
| CN117014471A (en) | Engineering thing networking safety monitoring system based on artificial intelligence | |
| CN110533115B (en) | Quantitative evaluation method for transmission characteristics of track circuit based on variational modal decomposition | |
| CN110866558A (en) | Multi-source data fusion analysis-based rotating equipment state early warning method | |
| CN205449522U (en) | Track structure operating condition monitoring system | |
| ITUB20155449A1 (en) | METHOD OF ANALYSIS OF A TEMPORAL SEQUENCE OF MEASURES OF A CHARACTERISTIC SIGNAL OF A SYSTEM FOR THE PREVENTIVE SYSTEM DIAGNOSIS OF THE SAME SYSTEM | |
| CN113091949B (en) | Cable state detection method, device and equipment | |
| CN103472774A (en) | Real-time monitoring system and method of power tunnel | |
| KR20220009058A (en) | Learning method of artificial intelligence part for monitoring system of cable-supported bridge and the artificial intelligence part | |
| JP3968437B2 (en) | Life change detection method, apparatus and program | |
| JP2013149249A (en) | System and method for monitoring, diagnosis, and predictive diagnosis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |
|
| RJ01 | Rejection of invention patent application after publication |